diff --git "a/config.json" "b/config.json" --- "a/config.json" +++ "b/config.json" @@ -1,2865 +1,2883 @@ { - "architectures": [ - "Mistral3ForConditionalGeneration" - ], - "dtype": "bfloat16", - "eos_token_id": 2, - "image_token_index": 10, - "model_type": "mistral3", - "multimodal_projector_bias": false, - "projector_hidden_act": "gelu", - "quantization": { - "group_size": 32, - "bits": 4, - "mode": "affine", - "language_model.model.embed_tokens": { - "group_size": 64, - "bits": 8, - "mode": "affine" - }, - "language_model.model.layers.0.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.0.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.0.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.0.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.0.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.0.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.0.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.1.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.1.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.1.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.1.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.1.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.1.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.1.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.2.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.2.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.2.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.2.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.2.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.2.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.2.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.3.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.3.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.3.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.3.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.3.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.3.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.3.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.4.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.4.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.4.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.4.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.4.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.4.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.4.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.5.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.5.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.5.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.5.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.5.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.5.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.5.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.6.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.6.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.6.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.6.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.6.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.6.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.6.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.7.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.7.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.7.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.7.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.7.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.7.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.7.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.8.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.8.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.8.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.8.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.8.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.8.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.8.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.9.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.9.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.9.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.9.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.9.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.9.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.9.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.10.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.10.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.10.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.10.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.10.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.10.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.10.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.11.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.11.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.11.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.11.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.11.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.11.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.11.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.12.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.12.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.12.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.12.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.12.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.12.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.12.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.13.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.13.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.13.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.13.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.13.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.13.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.13.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.14.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.14.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.14.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.14.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.14.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.14.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.14.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.15.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.15.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.15.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.15.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.15.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.15.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.15.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.16.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.16.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.16.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.16.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.16.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.16.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.16.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.17.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.17.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.17.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.17.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.17.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.17.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.17.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.18.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.18.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.18.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.18.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.18.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.18.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.18.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.19.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.19.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.19.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.19.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.19.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.19.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.19.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.20.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.20.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.20.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.20.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.20.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.20.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.20.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.21.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.21.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.21.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.21.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.21.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.21.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.21.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.22.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.22.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.22.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.22.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.22.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.22.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.22.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.23.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.23.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.23.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.23.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.23.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.23.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.23.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.24.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.24.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.24.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.24.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.24.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.24.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.24.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.25.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.25.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.25.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.25.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.25.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.25.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.25.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.26.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.26.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.26.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.26.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.26.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.26.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.26.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.27.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.27.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.27.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.27.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.27.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.27.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.27.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.28.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.28.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.28.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.28.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.28.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.28.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.28.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.29.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.29.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.29.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.29.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.29.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.29.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.29.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.30.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.30.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.30.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.30.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.30.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.30.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.30.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.31.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.31.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.31.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.31.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.31.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.31.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.31.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.32.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.32.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.32.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.32.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.32.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.32.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.32.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.33.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.33.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.33.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.33.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.33.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.33.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.33.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.34.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.34.self_attn.k_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.34.self_attn.v_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.34.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.34.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.34.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.34.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.35.self_attn.q_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.35.self_attn.k_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.35.self_attn.v_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.35.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.35.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.35.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.35.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.36.self_attn.q_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.36.self_attn.k_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.36.self_attn.v_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.36.self_attn.o_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.36.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.36.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.36.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.37.self_attn.q_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.37.self_attn.k_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.37.self_attn.v_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.37.self_attn.o_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.37.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.37.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.37.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.38.self_attn.q_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.38.self_attn.k_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.38.self_attn.v_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.38.self_attn.o_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.38.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.38.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.38.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.39.self_attn.q_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.39.self_attn.k_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.39.self_attn.v_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.39.self_attn.o_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.39.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.39.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.39.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - } - }, - "quantization_config": { - "group_size": 32, - "bits": 4, - "mode": "affine", - "language_model.model.embed_tokens": { - "group_size": 64, - "bits": 8, - "mode": "affine" - }, - "language_model.model.layers.0.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.0.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.0.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.0.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.0.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.0.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.0.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.1.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.1.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.1.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.1.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.1.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.1.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.1.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.2.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.2.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.2.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.2.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.2.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.2.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.2.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.3.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.3.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.3.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.3.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.3.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.3.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.3.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.4.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.4.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.4.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.4.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.4.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.4.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.4.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.5.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.5.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.5.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.5.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.5.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.5.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.5.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.6.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.6.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.6.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.6.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.6.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.6.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.6.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.7.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.7.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.7.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.7.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.7.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.7.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.7.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.8.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.8.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.8.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.8.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.8.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.8.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.8.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.9.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.9.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.9.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.9.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.9.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.9.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.9.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.10.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.10.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.10.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.10.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.10.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.10.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.10.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.11.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.11.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.11.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.11.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.11.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.11.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.11.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.12.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.12.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.12.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.12.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.12.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.12.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.12.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.13.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.13.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.13.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.13.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.13.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.13.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.13.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.14.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.14.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.14.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.14.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.14.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.14.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.14.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.15.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.15.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.15.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.15.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.15.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.15.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.15.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.16.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.16.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.16.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.16.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.16.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.16.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.16.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.17.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.17.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.17.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.17.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.17.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.17.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.17.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.18.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.18.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.18.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.18.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.18.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.18.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.18.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.19.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.19.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.19.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.19.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.19.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.19.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.19.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.20.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.20.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.20.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.20.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.20.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.20.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.20.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.21.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.21.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.21.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.21.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.21.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.21.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.21.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.22.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.22.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.22.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.22.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.22.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.22.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.22.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.23.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.23.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.23.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.23.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.23.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.23.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.23.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.24.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.24.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.24.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.24.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.24.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.24.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.24.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.25.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.25.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.25.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.25.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.25.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.25.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.25.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.26.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.26.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.26.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.26.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.26.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.26.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.26.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.27.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.27.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.27.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.27.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.27.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.27.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.27.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.28.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.28.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.28.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.28.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.28.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.28.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.28.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.29.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.29.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.29.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.29.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.29.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.29.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.29.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.30.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.30.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.30.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.30.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.30.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.30.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.30.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.31.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.31.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.31.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.31.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.31.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.31.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.31.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.32.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.32.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.32.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.32.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.32.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.32.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.32.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.33.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.33.self_attn.k_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.33.self_attn.v_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.33.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.33.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.33.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.33.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.34.self_attn.q_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.34.self_attn.k_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.34.self_attn.v_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.34.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.34.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.34.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.34.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.35.self_attn.q_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.35.self_attn.k_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.35.self_attn.v_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.35.self_attn.o_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.35.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.35.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.35.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.36.self_attn.q_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.36.self_attn.k_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.36.self_attn.v_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.36.self_attn.o_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.36.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.36.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.36.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.37.self_attn.q_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.37.self_attn.k_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.37.self_attn.v_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.37.self_attn.o_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.37.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.37.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.37.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.38.self_attn.q_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.38.self_attn.k_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.38.self_attn.v_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.38.self_attn.o_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.38.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.38.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.38.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.39.self_attn.q_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.39.self_attn.k_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.39.self_attn.v_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.39.self_attn.o_proj": { - "group_size": 32, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.39.mlp.gate_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.39.mlp.down_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - }, - "language_model.model.layers.39.mlp.up_proj": { - "group_size": 64, - "bits": 4, - "mode": "affine" - } - }, - "spatial_merge_size": 2, - "text_config": { - "attention_dropout": 0.0, - "head_dim": 128, - "hidden_act": "silu", - "hidden_size": 5120, - "initializer_range": 0.02, - "intermediate_size": 16384, - "max_position_embeddings": 262144, - "model_type": "ministral3", - "num_attention_heads": 32, - "num_hidden_layers": 40, - "num_key_value_heads": 8, - "rms_norm_eps": 1e-05, - "rope_parameters": { - "beta_fast": 32.0, - "beta_slow": 1.0, - "factor": 16.0, - "llama_4_scaling_beta": 0.1, - "mscale": 1.0, - "mscale_all_dim": 1.0, - "original_max_position_embeddings": 16384, - "rope_theta": 1000000000.0, - "rope_type": "yarn", - "type": "yarn" - }, - "sliding_window": null, - "use_cache": true, - "vocab_size": 131072, - "tie_word_embeddings": false + "architectures": [ + "Mistral3ForConditionalGeneration" + ], + "dtype": "bfloat16", + "eos_token_id": 2, + "image_token_index": 10, + "model_type": "mistral3", + "multimodal_projector_bias": false, + "projector_hidden_act": "gelu", + "quantization": { + "bits": 4, + "group_size": 32, + "language_model.model.embed_tokens": { + "bits": 8, + "group_size": 64, + "mode": "affine" }, + "language_model.model.layers.0.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.0.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.0.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.0.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.0.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.0.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.0.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.1.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.1.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.1.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.1.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.1.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.1.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.1.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.10.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.10.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.10.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.10.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.10.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.10.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.10.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.11.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.11.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.11.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.11.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.11.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.11.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.11.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.12.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.12.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.12.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.12.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.12.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.12.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.12.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.13.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.13.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.13.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.13.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.13.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.13.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.13.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.14.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.14.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.14.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.14.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.14.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.14.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.14.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.15.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.15.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.15.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.15.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.15.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.15.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.15.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.16.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.16.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.16.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.16.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.16.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.16.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.16.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.17.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.17.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.17.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.17.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.17.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.17.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.17.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.18.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.18.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.18.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.18.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.18.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.18.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.18.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.19.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.19.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.19.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.19.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.19.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.19.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.19.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.2.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.2.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.2.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.2.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.2.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.2.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.2.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.20.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.20.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.20.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.20.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.20.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.20.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.20.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.21.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.21.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.21.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.21.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.21.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.21.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.21.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.22.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.22.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.22.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.22.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.22.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.22.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.22.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.23.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.23.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.23.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.23.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.23.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.23.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.23.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.24.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.24.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.24.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.24.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.24.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.24.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.24.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.25.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.25.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.25.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.25.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.25.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.25.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.25.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.26.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.26.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.26.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.26.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.26.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.26.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.26.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.27.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.27.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.27.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.27.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.27.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.27.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.27.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.28.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.28.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.28.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.28.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.28.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.28.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.28.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.29.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.29.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.29.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.29.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.29.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.29.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.29.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.3.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.3.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.3.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.3.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.3.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.3.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.3.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.30.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.30.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.30.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.30.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.30.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.30.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.30.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.31.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.31.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.31.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.31.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.31.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.31.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.31.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.32.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.32.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.32.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.32.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.32.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.32.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.32.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.33.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.33.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.33.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.33.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.33.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.33.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.33.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.34.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.34.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.34.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.34.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.34.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.34.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.34.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.35.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.35.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.35.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.35.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.35.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.35.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.35.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.36.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.36.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.36.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.36.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.36.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.36.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.36.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.37.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.37.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.37.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.37.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.37.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.37.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.37.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.38.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.38.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.38.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.38.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.38.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.38.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.38.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.39.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.39.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.39.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.39.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.39.self_attn.o_proj": { + "bits": 4, + "group_size": 32, + "mode": "affine" + }, + "language_model.model.layers.39.self_attn.q_proj": { + "bits": 4, + "group_size": 32, + "mode": "affine" + }, + "language_model.model.layers.39.self_attn.v_proj": { + "bits": 4, + "group_size": 32, + "mode": "affine" + }, + "language_model.model.layers.4.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.4.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.4.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.4.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.4.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.4.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.4.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.5.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.5.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.5.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.5.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.5.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.5.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.5.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.6.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.6.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.6.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.6.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.6.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.6.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.6.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.7.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.7.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.7.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.7.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.7.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.7.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.7.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.8.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.8.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.8.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.8.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.8.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.8.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.8.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.9.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.9.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.9.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.9.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.9.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.9.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.9.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "mode": "affine" + }, + "quantization_config": { + "bits": 4, + "group_size": 32, + "language_model.model.embed_tokens": { + "bits": 8, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.0.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.0.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.0.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.0.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.0.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.0.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.0.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.1.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.1.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.1.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.1.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.1.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.1.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.1.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.10.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.10.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.10.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.10.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.10.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.10.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.10.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.11.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.11.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.11.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.11.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.11.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.11.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.11.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.12.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.12.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.12.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.12.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.12.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.12.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.12.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.13.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.13.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.13.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.13.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.13.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.13.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.13.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.14.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.14.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.14.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.14.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.14.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.14.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.14.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.15.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.15.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.15.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.15.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.15.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.15.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.15.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.16.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.16.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.16.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.16.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.16.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.16.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.16.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.17.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.17.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.17.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.17.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.17.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.17.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.17.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.18.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.18.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.18.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.18.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.18.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.18.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.18.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.19.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.19.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.19.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.19.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.19.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.19.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.19.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.2.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.2.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.2.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.2.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.2.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.2.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.2.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.20.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.20.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.20.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.20.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.20.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.20.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.20.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.21.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.21.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.21.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.21.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.21.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.21.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.21.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.22.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.22.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.22.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.22.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.22.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.22.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.22.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.23.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.23.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.23.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.23.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.23.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.23.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.23.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.24.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.24.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.24.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.24.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.24.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.24.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.24.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.25.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.25.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.25.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.25.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.25.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.25.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.25.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.26.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.26.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.26.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.26.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.26.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.26.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.26.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.27.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.27.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.27.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.27.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.27.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.27.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.27.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.28.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.28.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.28.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.28.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.28.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.28.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.28.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.29.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.29.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.29.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.29.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.29.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.29.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.29.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.3.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.3.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.3.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.3.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.3.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.3.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.3.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.30.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.30.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.30.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.30.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.30.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.30.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.30.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.31.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.31.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.31.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.31.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.31.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.31.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.31.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.32.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.32.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.32.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.32.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.32.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.32.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.32.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.33.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.33.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.33.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.33.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.33.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.33.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.33.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.34.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.34.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.34.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.34.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.34.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.34.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.34.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.35.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.35.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.35.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.35.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.35.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.35.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.35.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.36.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.36.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.36.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.36.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.36.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.36.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.36.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.37.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.37.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.37.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.37.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.37.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.37.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.37.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.38.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.38.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.38.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.38.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.38.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.38.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.38.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.39.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.39.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.39.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.39.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.39.self_attn.o_proj": { + "bits": 4, + "group_size": 32, + "mode": "affine" + }, + "language_model.model.layers.39.self_attn.q_proj": { + "bits": 4, + "group_size": 32, + "mode": "affine" + }, + "language_model.model.layers.39.self_attn.v_proj": { + "bits": 4, + "group_size": 32, + "mode": "affine" + }, + "language_model.model.layers.4.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.4.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.4.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.4.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.4.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.4.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.4.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.5.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.5.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.5.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.5.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.5.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.5.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.5.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.6.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.6.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.6.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.6.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.6.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.6.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.6.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.7.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.7.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.7.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.7.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.7.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.7.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.7.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.8.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.8.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.8.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.8.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.8.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.8.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.8.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.9.mlp.down_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.9.mlp.gate_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.9.mlp.up_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.9.self_attn.k_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.9.self_attn.o_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.9.self_attn.q_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "language_model.model.layers.9.self_attn.v_proj": { + "bits": 4, + "group_size": 64, + "mode": "affine" + }, + "mode": "affine" + }, + "spatial_merge_size": 2, + "text_config": { + "attention_dropout": 0.0, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 16384, + "max_position_embeddings": 262144, + "model_type": "ministral3", + "num_attention_heads": 32, + "num_hidden_layers": 40, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "beta_fast": 32.0, + "beta_slow": 1.0, + "factor": 16.0, + "llama_4_scaling_beta": 0.1, + "mscale": 1.0, + "mscale_all_dim": 1.0, + "original_max_position_embeddings": 16384, + "rope_theta": 1000000000.0, + "rope_type": "yarn", + "type": "yarn" + }, + "sliding_window": null, "tie_word_embeddings": false, - "transformers_version": "5.0.0.dev0", - "vision_feature_layer": -1 -} \ No newline at end of file + "use_cache": true, + "vocab_size": 131072 + }, + "transformers_version": "5.0.0.dev0", + "vision_config": { + "attention_dropout": 0.0, + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 1024, + "image_size": 1540, + "initializer_range": 0.02, + "intermediate_size": 4096, + "model_type": "pixtral", + "num_attention_heads": 16, + "num_channels": 3, + "num_hidden_layers": 24, + "patch_size": 14, + "rope_parameters": { + "rope_theta": 10000.0, + "rope_type": "default" + }, + "rope_theta": 10000.0 + }, + "vision_feature_layer": -1 +}